How are vaccination drives going + the inequalities underneath

import plotly
plotly.offline.init_notebook_mode()

import numpy as np 
import pandas as pd 

# from google.colab import files
# uploaded = files.upload()

# from google.colab import files
# uploaded = files.upload()

df1=pd.read_csv("data\country_vaccinations.csv")

df2=pd.read_csv("data\country_vaccinations_by_manufacturer.csv")

df1.head()

	country	iso_code	date	total_vaccinations	people_vaccinated	people_fully_vaccinated	daily_vaccinations_raw	daily_vaccinations	total_vaccinations_per_hundred	people_vaccinated_per_hundred	people_fully_vaccinated_per_hundred	daily_vaccinations_per_million	vaccines	source_name	source_website
0	Afghanistan	AFG	2021-02-22	0.0	0.0	NaN	NaN	NaN	0.0	0.0	NaN	NaN	Johnson&Johnson, Oxford/AstraZeneca, Pfizer/Bi...	World Health Organization	https://covid19.who.int/
1	Afghanistan	AFG	2021-02-23	NaN	NaN	NaN	NaN	1367.0	NaN	NaN	NaN	34.0	Johnson&Johnson, Oxford/AstraZeneca, Pfizer/Bi...	World Health Organization	https://covid19.who.int/
2	Afghanistan	AFG	2021-02-24	NaN	NaN	NaN	NaN	1367.0	NaN	NaN	NaN	34.0	Johnson&Johnson, Oxford/AstraZeneca, Pfizer/Bi...	World Health Organization	https://covid19.who.int/
3	Afghanistan	AFG	2021-02-25	NaN	NaN	NaN	NaN	1367.0	NaN	NaN	NaN	34.0	Johnson&Johnson, Oxford/AstraZeneca, Pfizer/Bi...	World Health Organization	https://covid19.who.int/
4	Afghanistan	AFG	2021-02-26	NaN	NaN	NaN	NaN	1367.0	NaN	NaN	NaN	34.0	Johnson&Johnson, Oxford/AstraZeneca, Pfizer/Bi...	World Health Organization	https://covid19.who.int/

df2.head()

	location	date	vaccine	total_vaccinations
0	Argentina	2020-12-29	Moderna	2
1	Argentina	2020-12-29	Oxford/AstraZeneca	3
2	Argentina	2020-12-29	Sinopharm/Beijing	1
3	Argentina	2020-12-29	Sputnik V	20481
4	Argentina	2020-12-30	Moderna	2

df1.describe()

	total_vaccinations	people_vaccinated	people_fully_vaccinated	daily_vaccinations_raw	daily_vaccinations	total_vaccinations_per_hundred	people_vaccinated_per_hundred	people_fully_vaccinated_per_hundred	daily_vaccinations_per_million
count	4.360700e+04	4.129400e+04	3.880200e+04	3.536200e+04	8.621300e+04	43607.000000	41294.000000	38802.000000	86213.000000
mean	4.592964e+07	1.770508e+07	1.413830e+07	2.705996e+05	1.313055e+05	80.188543	40.927317	35.523243	3257.049157
std	2.246004e+08	7.078731e+07	5.713920e+07	1.212427e+06	7.682388e+05	67.913577	29.290759	28.376252	3934.312440
min	0.000000e+00	0.000000e+00	1.000000e+00	0.000000e+00	0.000000e+00	0.000000	0.000000	0.000000	0.000000
25%	5.264100e+05	3.494642e+05	2.439622e+05	4.668000e+03	9.000000e+02	16.050000	11.370000	7.020000	636.000000
50%	3.590096e+06	2.187310e+06	1.722140e+06	2.530900e+04	7.343000e+03	67.520000	41.435000	31.750000	2050.000000
75%	1.701230e+07	9.152520e+06	7.559870e+06	1.234925e+05	4.409800e+04	132.735000	67.910000	62.080000	4682.000000
max	3.263129e+09	1.275541e+09	1.240777e+09	2.474100e+07	2.242429e+07	345.370000	124.760000	122.370000	117497.000000

df2.describe()

	total_vaccinations
count	3.562300e+04
mean	1.508357e+07
std	5.181768e+07
min	0.000000e+00
25%	9.777600e+04
50%	1.305506e+06
75%	7.932423e+06
max	6.005200e+08

import matplotlib.pyplot as plt
import seaborn as sns
import matplotlib
%matplotlib inline
import plotly.express as px
sns.set_style('darkgrid')
matplotlib.rcParams['font.size'] = 12
matplotlib.rcParams['figure.facecolor'] = '#00000000'
matplotlib.rcParams['figure.figsize'] = (10, 6)
plt.rc('font', size=11)

Let us try to perform the analysis for a particular country, say India

India_data=df1[df1["iso_code"]=="IND"]

India_data.head()

	country	iso_code	date	total_vaccinations	people_vaccinated	people_fully_vaccinated	daily_vaccinations_raw	daily_vaccinations	total_vaccinations_per_hundred	people_vaccinated_per_hundred	people_fully_vaccinated_per_hundred	daily_vaccinations_per_million	vaccines	source_name	source_website
35372	India	IND	2021-01-15	0.0	0.0	NaN	NaN	NaN	0.00	0.00	NaN	NaN	Covaxin, Oxford/AstraZeneca, Sputnik V	Government of India	https://dashboard.cowin.gov.in/
35373	India	IND	2021-01-16	191181.0	191181.0	NaN	191181.0	191181.0	0.01	0.01	NaN	137.0	Covaxin, Oxford/AstraZeneca, Sputnik V	Government of India	https://dashboard.cowin.gov.in/
35374	India	IND	2021-01-17	224301.0	224301.0	NaN	33120.0	112150.0	0.02	0.02	NaN	80.0	Covaxin, Oxford/AstraZeneca, Sputnik V	Government of India	https://dashboard.cowin.gov.in/
35375	India	IND	2021-01-18	454049.0	454049.0	NaN	229748.0	151350.0	0.03	0.03	NaN	109.0	Covaxin, Oxford/AstraZeneca, Sputnik V	Government of India	https://dashboard.cowin.gov.in/
35376	India	IND	2021-01-19	674835.0	674835.0	NaN	220786.0	168709.0	0.05	0.05	NaN	121.0	Covaxin, Oxford/AstraZeneca, Sputnik V	Government of India	https://dashboard.cowin.gov.in/

India_data.fillna(0) #Replacing NaN values with 0

	country	iso_code	date	total_vaccinations	people_vaccinated	people_fully_vaccinated	daily_vaccinations_raw	daily_vaccinations	total_vaccinations_per_hundred	people_vaccinated_per_hundred	people_fully_vaccinated_per_hundred	daily_vaccinations_per_million	vaccines	source_name	source_website
35372	India	IND	2021-01-15	0.000000e+00	0.0	0.0	0.0	0.0	0.00	0.00	0.00	0.0	Covaxin, Oxford/AstraZeneca, Sputnik V	Government of India	https://dashboard.cowin.gov.in/
35373	India	IND	2021-01-16	1.911810e+05	191181.0	0.0	191181.0	191181.0	0.01	0.01	0.00	137.0	Covaxin, Oxford/AstraZeneca, Sputnik V	Government of India	https://dashboard.cowin.gov.in/
35374	India	IND	2021-01-17	2.243010e+05	224301.0	0.0	33120.0	112150.0	0.02	0.02	0.00	80.0	Covaxin, Oxford/AstraZeneca, Sputnik V	Government of India	https://dashboard.cowin.gov.in/
35375	India	IND	2021-01-18	4.540490e+05	454049.0	0.0	229748.0	151350.0	0.03	0.03	0.00	109.0	Covaxin, Oxford/AstraZeneca, Sputnik V	Government of India	https://dashboard.cowin.gov.in/
35376	India	IND	2021-01-19	6.748350e+05	674835.0	0.0	220786.0	168709.0	0.05	0.05	0.00	121.0	Covaxin, Oxford/AstraZeneca, Sputnik V	Government of India	https://dashboard.cowin.gov.in/
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
35806	India	IND	2022-03-25	1.826266e+09	980435665.0	824764568.0	1997100.0	2433734.0	131.06	70.36	59.19	1747.0	Covaxin, Oxford/AstraZeneca, Sputnik V	Government of India	https://dashboard.cowin.gov.in/
35807	India	IND	2022-03-26	1.830285e+09	982687842.0	826360688.0	4019460.0	2830351.0	131.35	70.52	59.30	2031.0	Covaxin, Oxford/AstraZeneca, Sputnik V	Government of India	https://dashboard.cowin.gov.in/
35808	India	IND	2022-03-27	1.831348e+09	983190780.0	826884564.0	1062451.0	2851859.0	131.43	70.56	59.34	2047.0	Covaxin, Oxford/AstraZeneca, Sputnik V	Government of India	https://dashboard.cowin.gov.in/
35809	India	IND	2022-03-28	1.833040e+09	984051283.0	827610878.0	1692273.0	2736644.0	131.55	70.62	59.39	1964.0	Covaxin, Oxford/AstraZeneca, Sputnik V	Government of India	https://dashboard.cowin.gov.in/
35810	India	IND	2022-03-29	1.834501e+09	984838143.0	828229455.0	1460643.0	2580123.0	131.66	70.68	59.44	1852.0	Covaxin, Oxford/AstraZeneca, Sputnik V	Government of India	https://dashboard.cowin.gov.in/

439 rows × 15 columns

plt.figure(figsize=(20,5))
sns.lineplot(data=India_data,x="date",y="daily_vaccinations",marker='*',markersize= 8)
plt.title("Per day vaccinations population trend in India")

plt.tight_layout()
plt.show();

Let us now observe the trend for USA

df4=India_data.iloc[::25][:]
df4=df4[1:][:]
df4.head()
# India_data_copy=df4[df4["iso_code"]=="IND"]
plt.figure(figsize=(25,9))
sns.lineplot(data=df4,x="date",y="daily_vaccinations",marker='*',markersize= 15)
plt.title("Per day vaccinations population trend in INDIA")

plt.tight_layout()

RUS_data=df1[df1["iso_code"]=="RUS"]
df5=RUS_data.iloc[::25][:]
df5.head()
# India_data_copy=df4[df4["iso_code"]=="IND"]
plt.figure(figsize=(25,9))
sns.lineplot(data=df5,x="date",y="daily_vaccinations",marker='*',markersize= 15)
plt.title("Per day vaccinations population trend in RUSSIA")

plt.tight_layout()

CHINA_data=df1[df1["iso_code"]=="CHN"]
df6=CHINA_data.iloc[::25][:]
# df6.head()

plt.figure(figsize=(25,9))
sns.lineplot(data=df6,x="date",y="daily_vaccinations",marker='*',markersize= 15)
plt.title("Per day vaccinations population trends in CHINA")
plt.tight_layout()
plt.show();

unique_country_codes=df1.iso_code.unique()

# print(unique_country_codes)
total_vaccinations=[]
for i in unique_country_codes:
  country_data=df1[df1["iso_code"]==i]
  total_vaccinations.append([country_data['total_vaccinations_per_hundred'].sum()/len(df1),i])

total_vaccinations.sort(reverse=True)


plt.figure(figsize=(25,9))
plt.xticks(rotation=45)

#top 20 

countries=total_vaccinations[:20]

country_codes=[countries[i][1] for i in range(len(countries))]
vaccinated=[countries[i][0] for i in range(len(country_codes))]

# print(vaccinated)
plt.title("Top 20 countries according to the population vaccinated per hundred on an average")
plt.bar(country_codes,vaccinated)

<BarContainer object of 20 artists>

unique_country_codes=df1.iso_code.unique()

# print(unique_country_codes)
total_vaccinations=[]
for i in unique_country_codes:
  country_data=df1[df1["iso_code"]==i]
  total_vaccinations.append([country_data['total_vaccinations'].sum(),i])

total_vaccinations.sort(reverse=True)


plt.figure(figsize=(25,9))
plt.xticks(rotation=45)

#top 20 

countries=total_vaccinations[:20]

country_codes=[countries[i][1] for i in range(len(countries))]
vaccinated=[countries[i][0] for i in range(len(country_codes))]

# print(vaccinated)
plt.title("Top 20 countries according to the total population vaccinated")
plt.bar(country_codes,vaccinated,color = 'g')

<BarContainer object of 20 artists>

unique_country_codes=df1.iso_code.unique()
print(len(unique_country_codes))
# print(unique_country_codes)
total_vaccinations=[]
for i in unique_country_codes:
  country_data=df1[df1["iso_code"]==i]
  total_vaccinations.append([country_data['total_vaccinations_per_hundred'].sum()/len(df1),i])

total_vaccinations.sort()


plt.figure(figsize=(25,9))
plt.xticks(rotation=45)

#top 20 

countries=total_vaccinations[:20]

country_codes=[countries[i][1] for i in range(len(countries))]
vaccinated=[countries[i][0] for i in range(len(country_codes))]

# print(vaccinated)
plt.title("Least 20 countries according to the population vaccinated per hundred on an average")
plt.bar(country_codes,vaccinated)

223

<BarContainer object of 20 artists>

unique_country_codes=df1.iso_code.unique()
print(len(unique_country_codes))
# print(unique_country_codes)
total_vaccinations=[]
for i in unique_country_codes:
  country_data=df1[df1["iso_code"]==i]
  total_vaccinations.append([country_data['people_fully_vaccinated'].sum(),country_data['total_vaccinations'].sum()-country_data['people_fully_vaccinated'].sum(),i])

total_vaccinations.sort(key=lambda x : x[1]-x[0],reverse=True)


plt.figure(figsize=(25,9))
plt.xticks(rotation=45)

#top 20 

countries=total_vaccinations[:20]
print(countries)
country_codes=[countries[i][2] for i in range(len(countries))]
first_dose_vaccinated=[countries[i][1] for i in range(len(country_codes))]
fully_vaccinated=[countries[i][0] for i in range(len(country_codes))]
# print(vaccinated)
plt.title("Top 20 countries according to the total population vaccinated")
# plt.bar(country_codes,vaccinated,color = 'g')


width = 0.25

plt.bar(country_codes, first_dose_vaccinated, color = 'b',
		width = width, edgecolor = 'black',
		label='first_dose')
plt.bar(country_codes, fully_vaccinated, color = 'g',
		width = width, edgecolor = 'black',
		label='fully_vaccinated')


plt.legend()
plt.ylim(0, 15e10)

223
[[35263365000.0, 674189298700.0, 'CHN'], [116436444996.0, 207003860802.0, 'IND'], [66636073783.0, 88377793425.0, 'USA'], [30276933880.0, 48790240515.0, 'BRA'], [2790327552.0, 15124171600.0, 'VNM'], [14031369961.0, 22820271807.0, 'GBR'], [13059057856.0, 20864043077.0, 'TUR'], [11804284068.0, 19232829955.0, 'OWID_ENG'], [16199397881.0, 22783432451.0, 'DEU'], [13032980027.0, 19144059345.0, 'FRA'], [12123170801.0, 17589883231.0, 'ITA'], [7109532830.0, 11569418458.0, 'ARG'], [8725916008.0, 13105490027.0, 'KOR'], [12126072350.0, 16258490357.0, 'RUS'], [8014596169.0, 12003758151.0, 'THA'], [7375066347.0, 10853203300.0, 'CAN'], [12534314850.0, 15981155525.0, 'MEX'], [6237563902.0, 9440322436.0, 'PAK'], [5082636380.0, 8122442034.0, 'BGD'], [13645790941.0, 16656335987.0, 'JPN']]

(0.0, 150000000000.0)

Analyzing the trends of the companies manufacturing the vaccines

labels=df2.vaccine.unique()

vaccine = df2.groupby(["vaccine"])['total_vaccinations'].max().reset_index()
print(vaccine)


vaccine.percent = (vaccine.total_vaccinations/vaccine.total_vaccinations.sum())*100
# print(vaccine.percent)

wedgeprops = {"linewidth": 4, 'width':1, "edgecolor":"k"} # Width = 1
textprops = {"fontsize":15}
# plt.xticks(rotation=45);
plt.pie('total_vaccinations',labels = labels, data = vaccine,radius = 2,wedgeprops = wedgeprops,
        textprops=textprops, labeldistance = 0.6,);
plt.legend() # To show legend

              vaccine  total_vaccinations
0             CanSino              610540
1             Covaxin                  11
2     Johnson&Johnson            18563903
3             Moderna           210341785
4             Novavax              184429
5  Oxford/AstraZeneca            67403106
6     Pfizer/BioNTech           600519998
7   Sinopharm/Beijing            28322602
8             Sinovac            25596927
9           Sputnik V            20405678

C:\Users\HP\AppData\Local\Temp/ipykernel_22176/1190577492.py:7: UserWarning:

Pandas doesn't allow columns to be created via a new attribute name - see https://pandas.pydata.org/pandas-docs/stable/indexing.html#attribute-access

<matplotlib.legend.Legend at 0x1bef7aada60>

df2.head()

	location	date	vaccine	total_vaccinations
0	Argentina	2020-12-29	Moderna	2
1	Argentina	2020-12-29	Oxford/AstraZeneca	3
2	Argentina	2020-12-29	Sinopharm/Beijing	1
3	Argentina	2020-12-29	Sputnik V	20481
4	Argentina	2020-12-30	Moderna	2

import plotly.express as px

fig = px.choropleth(df1, locations="iso_code",
                    color="vaccines",
                    hover_name="country", 
                    color_continuous_scale=px.colors.sequential.Plasma,
                   title= "Vaccines used by different countries")



fig.update_layout(showlegend=True)
fig.show()

fig = px.choropleth(df1, locations="iso_code",
                    color="source_name",
                    hover_name="country", 
                    color_continuous_scale=px.colors.sequential.Plasma,
                   title= "Sources of vaccines for different countries")



fig.update_layout(showlegend=True)
fig.show()

plt.figure(figsize=(30,20))
sns.countplot(y='source_name', data=df1) 

<AxesSubplot:xlabel='count', ylabel='source_name'>

plt.figure(figsize=(20,10))
sns.countplot(y='vaccine', data=df2) 

<AxesSubplot:xlabel='count', ylabel='vaccine'>

fig = px.scatter_geo(df1, locations="iso_code", color="vaccines",
                     hover_name="country",
                     projection="natural earth", template="plotly_dark")

fig.show()

fig = px.scatter_geo(df1, locations="iso_code", color="people_vaccinated",
                     hover_name="country", 
                     projection="natural earth", animation_frame="date", template="plotly_dark")

fig.show()